Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 24217
    Prev
    Next
    INDEX
    Explanations

    economic terms and references

    oai_token-act-pair · gpt-3.5-turbo

    terms related to economic concepts and opportunities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rors
    -0.75
     stret
    -0.69
     forever
    -0.67
     retake
    -0.65
     hooked
    -0.65
     spray
    -0.63
    strip
    -0.62
    []
    -0.62
    init
    -0.62
    witch
    -0.62
    POSITIVE LOGITS
     Economic
    3.66
    Economic
    2.65
     economic
    1.97
    economic
    1.81
     Econom
    1.78
     Economics
    1.77
    Econom
    1.68
     Monetary
    1.63
     Economy
    1.46
     Fiscal
    1.46
    Activations Density 0.014%

    No Known Activations